论文标题
学习形状生成的学习梯度领域
Learning Gradient Fields for Shape Generation
论文作者
论文摘要
在这项工作中，我们提出了一种新型技术，可以从点云数据产生形状。点云可以看作是来自3D点的分布的样品，其密度集中在形状表面附近。因此，点云的产生等于将随机采样点移动到高密度区域。我们通过在非均衡概率密度上进行随机梯度上升来产生点云，从而将采样点移向高象形区域。我们的模型直接预测了对数密度场的梯度，并且可以通过基于得分的生成模型的简单目标进行训练。我们表明，我们的方法可以达到点云自动编码和生成的最新性能，同时还可以提取高质量的隐式表面。代码可在https://github.com/ruojincai/shapegf上找到。
In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. Point cloud generation thus amounts to moving randomly sampled points to high-density areas. We generate point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted from score-based generative models. We show that our method can reach state-of-the-art performance for point cloud auto-encoding and generation, while also allowing for extraction of a high-quality implicit surface. Code is available at https://github.com/RuojinCai/ShapeGF.
